In [1]:
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
1. Read the dataset.¶
In [2]:
data = pd.read_csv('pubg_dataset.csv')
data.head()
Out[2]:
2. Check the datatype of all the columns.¶
In [3]:
data.info()
3. Find the summary of all the numerical columns and write your findings about it.¶
In [4]:
data.describe()
Out[4]:
4. The average person kills how many players?¶
In [5]:
print("The average person kills",data['kills'].mean(),"players.")
5. 99% of people have how many kills?¶
In [6]:
print("99% of people have",np.percentile(data['kills'],99),"kills.")
6. The most kills ever recorded are how much?¶
In [7]:
print("The most kills ever recorded:",data['kills'].max())
7. Print all the columns of the dataframe.¶
In [8]:
data.columns
Out[8]:
8. Comment on distribution of the match's duration. Use seaborn.¶
In [9]:
sns.distplot(data['matchDuration']);
print("Within 1250 to 1500, match duration is high.")
9. Comment on distribution of the walk distance. Use seaborn.¶
In [10]:
sns.distplot(data['walkDistance']);
10. Plot distribution of the match's duration vs walk distance one below the other.¶
In [11]:
plt.style.use('seaborn')
plt.figure()
plt.subplot(2,1,1)
plt.plot(data['matchDuration'],'-')
plt.subplot(2,1,2)
plt.plot(data['walkDistance'],'-');
11. Plot distribution of the match's duration vs walk distance side by side.¶
In [12]:
plt.figure(figsize=(10,3))
plt.subplot(1,2,1)
plt.plot(data['matchDuration'],'-')
plt.subplot(1,2,2)
plt.plot(data['walkDistance'],'-');
12. Pairplot the dataframe. Comment on kills vs damage dealt, Comment on maxPlace vs numGroups.¶
In [13]:
sns.pairplot(data);
13. How many unique values are there in 'matchType' and what are their counts?¶
In [14]:
data['matchType'].value_counts()
Out[14]:
14. Plot a barplot of ‘matchType’ vs 'killPoints'. Write your inferences.¶
In [15]:
sns.barplot(x='matchType',y='killPoints',data=data);
plt.xticks(rotation=70);
15. Plot a barplot of ‘matchType’ vs ‘weaponsAcquired’. Write your inferences.¶
In [16]:
sns.barplot(x='matchType',y='weaponsAcquired',data=data);
plt.xticks(rotation=70);
16. Find the Categorical columns.¶
In [17]:
data.select_dtypes(['category']).columns
Out[17]:
17. Plot a boxplot of ‘matchType’ vs ‘winPlacePerc’. Write your inferences.¶
In [18]:
sns.boxplot(x='matchType',y='winPlacePerc',data=data);
plt.xticks(rotation=70);
18. Plot a boxplot of ‘matchType’ vs ‘matchDuration’. Write your inferences.¶
In [19]:
sns.boxplot(x='matchType',y='matchDuration',data=data);
plt.xticks(rotation=70);
19. Change the orientation of the above plot to horizontal.¶
In [20]:
sns.boxplot(x='matchDuration',y='matchType',data=data);
plt.xticks(rotation=70);
20. Add a new column called ‘KILL’ which contains the sum of following columns viz. headshotKills,teamKills, roadKills.¶
In [21]:
data['KILL'] = data['headshotKills'] + data['teamKills'] + data['roadKills']
data['KILL']
Out[21]:
21. Round off column ‘winPlacePerc’ to 2 decimals.¶
In [22]:
data['winPlacePerc'] = round(data['winPlacePerc'], 2)
data['winPlacePerc']
Out[22]:
22. Take a sample of size 50 from the column damageDealt for 100 times and calculate its mean. Plot it on a histogram and comment on its distribution.¶
In [35]:
data_arr = []
for i in range(100):
data_arr.append(data['damageDealt'].sample(50).mean())
sns.distplot(data_arr);
plt.xlabel('damageDealt');
